HiDream-E1.1 lifts low-res images to HD; strongest on anime and illustration styles.
Image Generation
Create unique visuals from text prompts using SDXL/Flux models. Ideal for designers needing rapid concept visualization.
Turn one image into a Ghibli-style image, then animate it into a Ghibli-style video with Wan.
FLUX.1-Krea-dev text-to-image with a distinctive aesthetic; fp8 default keeps VRAM low.
ByteDance USO on FLUX unifies subject-driven and style-driven image generation in one pass.
Consistent AI character from any angle: PuLID-Flux faces, OpenPose, DeepSeek prompts, Flux detail.
Style any image automatically: Florence2 captions it, you pick a style, the blend is generated.
Batch-remove or add watermarks across many images with SAM, GroundingDINO, and diffusion.
Strip clothing from a person in an image with segmentation, Flux redraw, and prompt tuning.
Consistent AI character sheets across poses and angles from a prompt and skeleton diagram.
ComfyUI Image Generation Workflows
Generate images from text prompts with ComfyUI. This category covers the core image generation workflows built on SDXL, Flux, and other stable diffusion models โ covering concept art, illustrations, product mockups, and stylized portraits. Each template is a ready-to-run node graph combining checkpoint models, samplers, and prompt controls; load it into ComfyUI and start from a working pipeline instead of a blank canvas. Browse the image generation templates below.